© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8688
    Prev
    Next
    INDEX
    Explanations

    biology studies and classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĶå®ĺ
    -0.10
    å½ĵäºĭ
    -0.10
    odore
    -0.09
    æĹłåģ¿
    -0.09
    æľĪä¸ĭ
    -0.09
    è½°
    -0.09
    çŁ¥éģĵèĩªå·±
    -0.09
    odor
    -0.08
    çĶ·
    -0.08
    charg
    -0.08
    POSITIVE LOGITS
    éĤ£æŶ
    0.09
    对人ä½ĵ
    0.08
    ocab
    0.08
    éĤ£æŶåĢĻ
    0.08
    cob
    0.08
    CHAN
    0.08
    åıĸå¾ĹäºĨ
    0.08
    GC
    0.08
    tour
    0.08
    EEDED
    0.08
    Activations Density 0.053%

    No Known Activations